util.py

# https://deeplearningcourses.com/c/unsupervised-deep-learning-in-python
# https://www.udemy.com/unsupervised-deep-learning-in-python
from __future__ import print_function, division
from builtins import range
# Note: you may need to update your version of future
# sudo pip install -U future

import numpy as np
import pandas as pd

from sklearn.utils import shuffle

def relu(x):
    return x * (x > 0)


def error_rate(p, t):
    return np.mean(p != t)


def getKaggleMNIST():
    # MNIST data:
    # column 0 is labels
    # column 1-785 is data, with values 0 .. 255
    # total size of CSV: (42000, 1, 28, 28)
    train = pd.read_csv('../large_files/train.csv').values.astype(np.float32)
    train = shuffle(train)

    Xtrain = train[:-1000,1:] / 255
    Ytrain = train[:-1000,0].astype(np.int32)

    Xtest  = train[-1000:,1:] / 255
    Ytest  = train[-1000:,0].astype(np.int32)
    return Xtrain, Ytrain, Xtest, Ytest


def init_weights(shape):
    w = np.random.randn(*shape) / np.sqrt(sum(shape))
    return w.astype(np.float32)